© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 6940
    Prev
    Next
    INDEX
    Explanations

    descriptive words related to book reviews such as "slow," "generic," and "entertaining."

    oai_token-act-pair · gpt-3.5-turbo

    evaluations and critiques of storytelling quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    continental
    -0.77
    reprene
    -0.77
     leased
    -0.76
    bred
    -0.74
    iership
    -0.72
    acion
    -0.69
    atlantic
    -0.69
    IFIED
    -0.69
     dreamed
    -0.68
     prohibited
    -0.67
    POSITIVE LOGITS
    Overall
    1.24
    Characters
    1.20
     gore
    1.07
     Characters
    0.98
    Gameplay
    0.97
     honestly
    0.96
     Overall
    0.93
     Helpful
    0.91
     pacing
    0.88
     cinem
    0.86
    Activations Density 0.849%

    No Known Activations